Papers › Alleviating Sequence Information Loss with Data Overlapping and Prime Batch Sizes

Alleviating Sequence Information Loss with Data Overlapping and Prime Batch Sizes

18 Sep 2019CONLL 2019 11arXiv:1909.08700archive 2025-07-28

Noémien Kocher, Christian Scuito, Lorenzo Tarantino, Alexandros Lazaridis, Andreas Fischer, Claudiu Musat

In sequence modeling tasks the token order matters, but this information can be partially lost due to the discretization of the sequence into data points. In this paper, we study the imbalance between the way certain token pairs are included in data points and others are not. We denote this a token order imbalance (TOI) and we link the partial sequence information loss to a diminished performance of the system as a whole, both in text and speech processing tasks. We then provide a mechanism to leverage the full token order information -Alleviated TOI- by iteratively overlapping the token composition of data points. For recurrent networks, we use prime numbers for the batch size to avoid redundancies when building batches from overlapped data points. The proposed method achieved state of the art performance in both text and speech related tasks.

PaperPDFConference PDFCode

Syntology This paper's arXiv id is not in Syntology's Atlas id list (549,449 ids, as this build read them; the read time is in the build record), so this page links to no Syntology page for it. The list is not the whole graph; Syntology's feed shows papers as they enter the graph.

Code

nkcr/overlap-ml officialmentioned in papermentioned on GitHubpytorchBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Breaking the Softmax Bottleneck: A High-Rank RNN Language Model (arXiv:1711.03953; that paper's own run record: 12 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 1 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Language Modelling

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Language Modelling WikiText-103 AWD-LSTM-MoS + ATOI Test perplexity 32.85 #74 of 89 Archive leaderboard report
Language Modelling WikiText-103 AWD-LSTM-MoS + ATOI Validation perplexity 31.92 #74 of 89 Archive leaderboard report
Language Modelling WikiText-2 AWD-LSTM + ATOI Number of params 33M #30 of 38 Archive leaderboard report
Language Modelling WikiText-2 AWD-LSTM + ATOI Test perplexity 64.73 #30 of 38 Archive leaderboard report
Language Modelling WikiText-2 AWD-LSTM + ATOI Validation perplexity 67.47 #30 of 38 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections